Exploratory Data Analysis of TV Streaming

import pandas as pd
pd.options.mode.chained_assignment = None
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns
sns.set() # setting seaborn default for plots
print("Setup Complete")

Setup Complete

import os

os.listdir()

['tv_shows.csv',
 '.DS_Store',
 '.jovianrc',
 '.ipynb_checkpoints',
 'streaming.ipynb']

raw_tv_shows_df = pd.read_csv('./tv_shows.csv', index_col=0)

raw_tv_shows_df.head()

	Title	Year	Age	IMDb	Rotten Tomatoes	Netflix	Hulu	Prime Video	Disney+	type
0	Breaking Bad	2008	18+	9.5	96%	1	0	0	0	1
1	Stranger Things	2016	16+	8.8	93%	1	0	0	0	1
2	Money Heist	2017	18+	8.4	91%	1	0	0	0	1
3	Sherlock	2010	16+	9.1	78%	1	0	0	0	1
4	Better Call Saul	2015	18+	8.7	97%	1	0	0	0	1

tv_shows_df = raw_tv_shows_df.copy()

tv_shows_df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 5611 entries, 0 to 5610
Data columns (total 10 columns):
 #   Column           Non-Null Count  Dtype  
---  ------           --------------  -----  
 0   Title            5611 non-null   object 
 1   Year             5611 non-null   int64  
 2   Age              3165 non-null   object 
 3   IMDb             4450 non-null   float64
 4   Rotten Tomatoes  1011 non-null   object 
 5   Netflix          5611 non-null   int64  
 6   Hulu             5611 non-null   int64  
 7   Prime Video      5611 non-null   int64  
 8   Disney+          5611 non-null   int64  
 9   type             5611 non-null   int64  
dtypes: float64(1), int64(6), object(3)
memory usage: 482.2+ KB

tv_shows_df.describe()

	Year	IMDb	Netflix	Hulu	Prime Video	Disney+	type
count	5611.000000	4450.000000	5611.000000	5611.000000	5611.000000	5611.000000	5611.0
mean	2011.021030	7.113258	0.344145	0.312600	0.382107	0.032080	1.0
std	11.005116	1.132060	0.475131	0.463594	0.485946	0.176228	0.0
min	1901.000000	1.000000	0.000000	0.000000	0.000000	0.000000	1.0
25%	2010.000000	6.600000	0.000000	0.000000	0.000000	0.000000	1.0
50%	2015.000000	7.300000	0.000000	0.000000	0.000000	0.000000	1.0
75%	2017.000000	7.900000	1.000000	1.000000	1.000000	0.000000	1.0
max	2020.000000	9.600000	1.000000	1.000000	1.000000	1.000000	1.0

tv_shows_df['Netflix'].sum()

1931

tv_shows_df['Hulu'].sum()

1754

tv_shows_df['Prime Video'].sum()

2144

tv_shows_df['Disney+'].sum()

180

Percent of shows that are 18+

(tv_shows_df['Age'] =='18+').sum()/tv_shows_df['Age'].count() *100

23.696682464454977

tv_shows_df['Age'].value_counts().sum()

3165

tv_shows_df['Age'].value_counts()

16+    1018
7+      848
18+     750
all     545
13+       4
Name: Age, dtype: int64

age_df = tv_shows_df['Age'].copy()

age_df['all'] = (age_df =='all').sum()/age_df.count() *100

age_df.all

<bound method Series.all of 0           18+
1           16+
2           18+
3           16+
4           18+
         ...   
5607        NaN
5608        NaN
5609        NaN
5610        NaN
all     17.2196
Name: Age, Length: 5612, dtype: object>

age_df

0           18+
1           16+
2           18+
3           16+
4           18+
         ...   
5607        NaN
5608        NaN
5609        NaN
5610        NaN
all     17.2196
Name: Age, Length: 5612, dtype: object

tv_shows_df['Age']

0       18+
1       16+
2       18+
3       16+
4       18+
       ... 
5606    NaN
5607    NaN
5608    NaN
5609    NaN
5610    NaN
Name: Age, Length: 5611, dtype: object

Per example, importing more libraries: https://www.kaggle.com/sreshta140/a-quick-analysis-on-tv-shows

from mpl_toolkits.mplot3d import Axes3D

import plotly.graph_objs as go

Converting Rotten Tomatoes score to a float

tv_shows_df['Rotten Tomatoes'] = tv_shows_df['Rotten Tomatoes'].str.replace('%', '')

tv_shows_df['Rotten Tomatoes'] = tv_shows_df['Rotten Tomatoes'].astype('float')

tv_shows_df['Rotten Tomatoes'].head()

0    96.0
1    93.0
2    91.0
3    78.0
4    97.0
Name: Rotten Tomatoes, dtype: float64

Correlation Matrix

corrmat = tv_shows_df.corr()
fig = plt.figure(figsize = (12, 9))

sns.heatmap(corrmat, vmax = .8, square = True, annot = True)
plt.show()

Finding top of IMBD:

top_imdb = tv_shows_df.sort_values(by=['IMDb'], ascending=False)
top_10_imdb = top_imdb.head(10)
top_10_imdb

	Title	Year	Age	IMDb	Rotten Tomatoes	Netflix	Hulu	Prime Video	Disney+	type
3023	Destiny	2014	NaN	9.6	NaN	0	1	0	0	1
0	Breaking Bad	2008	18+	9.5	96.0	1	0	0	0	1
3747	Malgudi Days	1987	all	9.5	NaN	0	0	1	0	1
3177	Hungry Henry	2014	NaN	9.5	NaN	0	1	0	0	1
3567	Band of Brothers	2001	18+	9.4	94.0	0	0	1	0	1
2365	The Joy of Painting	1983	all	9.4	NaN	0	1	1	0	1
4128	Green Paradise	2011	all	9.3	NaN	0	0	1	0	1
91	Our Planet	2019	7+	9.3	93.0	1	0	0	0	1
3566	The Wire	2002	18+	9.3	94.0	0	0	1	0	1
325	Ramayan	1987	all	9.3	NaN	1	0	0	0	1

Of these top 10 IMDb scores, how many are on streaming? How many on multiple streaming?

import plotly.express as px
fig = px.bar(top_10_imdb, y='IMDb', x='Title', color='IMDb')
fig.show()

How many movies were released each year?

yr = tv_shows_df['Year'].value_counts()
yr

2017    653
2016    573
2018    556
2015    454
2019    396
       ... 
1949      1
1934      1
1931      1
1943      1
1904      1
Name: Year, Length: 81, dtype: int64

yr = pd.DataFrame(yr)
yr=yr.reset_index()
yr=yr.rename(columns={'Year':'Count'})
yr=yr.rename(columns={'index': 'Year'})

import plotly.express as px
fig=px.bar(yr, x='Year', y='Count', color='Count')
fig.show()

age = tv_shows_df['Age'].value_counts()
age

16+    1018
7+      848
18+     750
all     545
13+       4
Name: Age, dtype: int64

age=age.reset_index()
age=age.rename(columns={'Age':'Count'})
age=age.rename(columns={'index': 'Age'})

fig=px.bar(age, x='Age', y='Count', color='Count')
fig.show()

fig = px.histogram(tv_shows_df, x='Rotten Tomatoes', nbins=100, opacity=0.8, color_discrete_sequence=['darkkhaki'])
fig.show()

analyzing the services:

netflix=tv_shows_df[tv_shows_df['Netflix']==1]
hulu=tv_shows_df[tv_shows_df['Hulu']==1]
prime=tv_shows_df[tv_shows_df['Prime Video']==1]
disney=tv_shows_df[tv_shows_df['Disney+']==1]
channels=[netflix, hulu, prime, disney]
cols=['Year', 'Age', 'IMDb']

tv_shows_list=[]
k = 0

for i in channels:
    col_list=[]
    for j in cols:
        a = i[j].value_counts()
        a = pd.DataFrame(a)
        a = a.reset_index()
        a = a.rename(columns={j: 'Count'})
        a = a.rename(columns={'index': j})
        col_list.append(a)
    tv_shows_list.append(col_list)

disney.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 180 entries, 472 to 5610
Data columns (total 10 columns):
 #   Column           Non-Null Count  Dtype  
---  ------           --------------  -----  
 0   Title            180 non-null    object 
 1   Year             180 non-null    int64  
 2   Age              150 non-null    object 
 3   IMDb             169 non-null    float64
 4   Rotten Tomatoes  24 non-null     float64
 5   Netflix          180 non-null    int64  
 6   Hulu             180 non-null    int64  
 7   Prime Video      180 non-null    int64  
 8   Disney+          180 non-null    int64  
 9   type             180 non-null    int64  
dtypes: float64(2), int64(6), object(2)
memory usage: 15.5+ KB

Years of movies in each service library:

import plotly.offline as pyoff
plot_data = [
    go.Bar(x=tv_shows_list[0][0]['Year'], y=tv_shows_list[0][0]['Count'], name='Netflix'),
    go.Bar(x=tv_shows_list[1][0]['Year'], y=tv_shows_list[1][0]['Count'], name='Hulu'),
    go.Bar(x=tv_shows_list[2][0]['Year'], y=tv_shows_list[2][0]['Count'], name='Prime Video'),
    go.Bar(x=tv_shows_list[3][0]['Year'], y=tv_shows_list[3][0]['Count'], name='Disney+'),
]
plot_layout = go.Layout(
        title='Year',
        yaxis_title='Count', 
        xaxis_title='Year'
    )
fig = go.Figure(data=plot_data, layout=plot_layout)
pyoff.iplot(fig)

plot_data = [
    go.Bar(x=tv_shows_list[0][1]['Age'], y=tv_shows_list[0][1]['Count'], name='Netflix'),
    go.Bar(x=tv_shows_list[1][1]['Age'], y=tv_shows_list[1][1]['Count'], name='Hulu'),
    go.Bar(x=tv_shows_list[2][1]['Age'], y=tv_shows_list[2][1]['Count'], name='Prime Video'),
    go.Bar(x=tv_shows_list[3][1]['Age'], y=tv_shows_list[3][1]['Count'], name='Disney+'),
]
plot_layout = go.Layout(
        title='Age',
        yaxis_title='Count', 
        xaxis_title='Age'
    )
fig = go.Figure(data=plot_data, layout=plot_layout)
pyoff.iplot(fig)

import plotly.offline as pyoff
plot_data = [
    go.Bar(x=tv_shows_list[0][2]['IMDb'], y=tv_shows_list[0][2]['Count'], name='Netflix'),
    go.Bar(x=tv_shows_list[1][2]['IMDb'], y=tv_shows_list[1][2]['Count'], name='Hulu'),
    go.Bar(x=tv_shows_list[2][2]['IMDb'], y=tv_shows_list[2][2]['Count'], name='Prime Video'),
    go.Bar(x=tv_shows_list[3][2]['IMDb'], y=tv_shows_list[3][2]['Count'], name='Disney+'),
]
plot_layout = go.Layout(
        title='IMDb',
        yaxis_title='Count', 
        xaxis_title='IMDb'
    )
fig = go.Figure(data=plot_data, layout=plot_layout)
pyoff.iplot(fig)

plot_data = [
    go.Histogram(x=netflix["Rotten Tomatoes"], name='Netflix'),
    go.Histogram(x=hulu["Rotten Tomatoes"], name='Hulu'),
    go.Histogram(x=prime["Rotten Tomatoes"], name='Prime Video'),
    go.Histogram(x=disney["Rotten Tomatoes"], name='Disney+')
]
plot_layout = go.Layout(
        title='Rotten Tomatoes',
        yaxis_title='Count',
        xaxis_title='Rotten Tomatoes'
    )
fig = go.Figure(data=plot_data, layout=plot_layout)
pyoff.iplot(fig)

Separating viewing platforms

netflix_shows = tv_shows_df.loc[tv_shows_df['Netflix']==1]
hulu_shows = tv_shows_df.loc[tv_shows_df['Hulu']==1]
prime_shows = tv_shows_df.loc[tv_shows_df['Prime Video']==1]
disney_shows = tv_shows_df.loc[tv_shows_df['Disney+']==1]

#dropping the unwanted columns

netflix_shows = netflix_shows.drop(['Hulu',
       'Prime Video', 'Disney+', 'type'], axis=1)
hulu_shows = hulu_shows.drop(['Netflix',
       'Prime Video', 'Disney+', 'type'], axis=1)
prime_shows = prime_shows.drop(['Netflix', 'Hulu',
        'Disney+', 'type'], axis=1)
disney_shows = disney_shows.drop(['Netflix', 'Hulu',
       'Prime Video', 'type'], axis=1)

netflix_shows.columns

Index(['Title', 'Year', 'Age', 'IMDb', 'Rotten Tomatoes', 'Netflix'], dtype='object')

hulu_shows.head()

	Title	Year	Age	IMDb	Rotten Tomatoes	Hulu
13	Attack on Titan	2013	16+	8.8	94.0	1
15	Fullmetal Alchemist: Brotherhood	2009	18+	9.1	100.0	1
16	Community	2009	7+	8.5	88.0	1
18	Parks and Recreation	2009	16+	8.6	93.0	1
22	Twin Peaks	1990	18+	8.8	89.0	1

index_netflix = netflix_shows.index
total_netflix = len(index_netflix)

index_hulu = hulu_shows.index
total_hulu = len(index_hulu)

index_prime = prime_shows.index
total_prime = len(index_prime)

index_disney = disney_shows.index
total_disney = len(index_disney)

#Pie Chart

labels = 'Netflix', 'Hulu', 'Prime Video', 'Disney+'
sizes = [total_netflix, total_hulu, total_prime, total_disney]
explode = (0.1, 0.1, 0.1, 0.1)

fig1, ax1 = plt.subplots()
ax1.pie(sizes,
       explode = explode,
       labels = labels,
       autopct = '%1.1f%%',
       shadow = True,
       startangle = 100)

ax1.axis('equal')
plt.show()

8+ ratings on IMDb

rate_show_netflix = netflix_shows['IMDb']>8
print("Total Movies on Netflix with more than 8+ rating(IMDb):", rate_show_netflix.sum())
rate_show_hulu = hulu_shows['IMDb']>8
print("Total Movies on Hulu with more than 8+ rating(IMDb):", rate_show_hulu.sum())
rate_show_prime = prime_shows['IMDb']>8
print("Total Movies on Prime Video with more than 8+ rating(IMDb):", rate_show_prime.sum())
rate_show_disney = disney_shows['IMDb']>8
print("Total Movies on Disney+ with more than 8+ rating(IMDb):", rate_show_disney.sum())

Total Movies on Netflix with more than 8+ rating(IMDb): 383
Total Movies on Hulu with more than 8+ rating(IMDb): 279
Total Movies on Prime Video with more than 8+ rating(IMDb): 293
Total Movies on Disney+ with more than 8+ rating(IMDb): 30

top_rated = [rate_show_netflix.sum(), rate_show_hulu.sum(), rate_show_prime.sum(), rate_show_disney.sum()]
top_plat = ['Netflix', 'Disney', 'Prime Video', 'Hulu']

top_rated_data = pd.DataFrame({
    'platforms': ['Netflix', 
                'Disney',
                'Prime Video',
                 'Hulu'],
    'total_show': [rate_show_netflix.sum(),
                 rate_show_disney.sum(),
                 rate_show_prime.sum(),
                 rate_show_hulu.sum()]
})

plt.figure(figsize=(10,10))
sns.barplot(data = top_rated_data,
           x = top_rated_data['platforms'],
           y = top_rated_data['total_show']
           )
plt.ylabel('Platform')
plt.xlabel('Total number of 8+ rated shows')
plt.title('Platform with most tv show rated above 8+ (IMDb)')
plt.show()

Rotten Tomatoes Rating:

rt_show_netflix = netflix_shows['Rotten Tomatoes']>=80
print("Total Movies on Netflix with more than 80 rating(Rotten Tomatoes):", rt_show_netflix.sum())
rt_show_hulu = hulu_shows['Rotten Tomatoes']>=80
print("Total Movies on Hulu with more than 80 rating(IMDb):", rt_show_hulu.sum())
rt_show_prime = prime_shows['Rotten Tomatoes']>=80
print("Total Movies on Prime Video with more than 80 rating(Rotten Tomatoes):", rt_show_prime.sum())
rt_show_disney = disney_shows['Rotten Tomatoes']>=80
print("Total Movies on Disney+ with more than 80 rating(Rotten Tomatoes):", rt_show_disney.sum())

Total Movies on Netflix with more than 80 rating(Rotten Tomatoes): 278
Total Movies on Hulu with more than 80 rating(IMDb): 229
Total Movies on Prime Video with more than 80 rating(Rotten Tomatoes): 129
Total Movies on Disney+ with more than 80 rating(Rotten Tomatoes): 17

rt_top_rated = [rt_show_netflix.sum(), rt_show_hulu.sum(), rt_show_prime.sum(), rt_show_disney.sum()]
rt_top_plat = ['Netflix', 'Disney', 'Prime Video', 'Hulu']

rt_top_rated_data = pd.DataFrame({
    'platforms': ['Netflix', 
                'Disney',
                'Prime Video',
                 'Hulu'],
    'total_show': [rt_show_netflix.sum(),
                 rt_show_disney.sum(),
                 rt_show_prime.sum(),
                 rt_show_hulu.sum()]
})

plt.figure(figsize=(10,10))
sns.barplot(data = rt_top_rated_data,
           x = rt_top_rated_data['platforms'],
           y = rt_top_rated_data['total_show']
           )
plt.ylabel('Platform')
plt.xlabel('Total number of 80+ Rotten Tomatoes ratings')
plt.title('Platform with most tv show rated above 80+ (Rotten Tomatoes)')
plt.show()

age_df2 = tv_shows_df.groupby('Age').groups
age_df2 = tv_shows_df.groupby('Age').sum()
age_df2[['Netflix', 'Hulu', 'Prime Video', 'Disney+']]

	Netflix	Hulu	Prime Video	Disney+
Age
13+	3	0	1	0
16+	398	514	209	3
18+	359	239	182	0
7+	300	365	224	66
all	171	159	192	81

sns.catplot(y='Age', kind='count', palette = 'pastel', edgecolor = '.6',
           data = tv_shows_df)

<seaborn.axisgrid.FacetGrid at 0x7f835bbee350>

Netflix count by age:

trace1 = go.Bar(x=age_df2.axes[0], y=age_df2['Netflix'], name='Netflix', 
                width=[0.5,0.5,0.5,0.5,0.5,])
x = [trace1]
layout = go.Layout(title='Count of Netflix content by age', legend=dict(x=0.1, y=0.1))
fig = go.Figure(x, layout=layout)
fig.update_traces(marker_color='rgb(102,216,23)', marker_line_color='rgb(87,96,107)', 
                 marker_line_width=1.5, opacity=0.6)
fig.show()

#HULU
trace2 = go.Bar(x=age_df2.axes[0], y=age_df2['Hulu'], name='Hulu', 
                width=[0.5,0.5,0.5,0.5,0.5,])
x = [trace2]
layout = go.Layout(title='Count of Hulu content by age', legend=dict(x=0.1, y=0.1))
fig = go.Figure(x, layout=layout)
fig.update_traces(marker_color='rgb(102,216,23)', marker_line_color='rgb(87,96,107)', 
                 marker_line_width=1.5, opacity=0.6)
fig.show()

#PRIME
trace3 = go.Bar(x=age_df2.axes[0], y=age_df2['Prime Video'], name='Prime Video', 
                width=[0.5,0.5,0.5,0.5,0.5,])
x = [trace3]
layout = go.Layout(title='Count of Prime content by age', legend=dict(x=0.1, y=0.1))
fig = go.Figure(x, layout=layout)
fig.update_traces(marker_color='rgb(102,216,23)', marker_line_color='rgb(87,96,107)', 
                 marker_line_width=1.5, opacity=0.6)
fig.show()

#DISNEY
trace4 = go.Bar(x=age_df2.axes[0], y=age_df2['Disney+'], name='Disney+', 
                width=[0.5,0.5,0.5,0.5,0.5,])
x = [trace4]
layout = go.Layout(title='Count of Netflix content by age', legend=dict(x=0.1, y=0.1))
fig = go.Figure(x, layout=layout)
fig.update_traces(marker_color='rgb(102,216,23)', marker_line_color='rgb(87,96,107)', 
                 marker_line_width=1.5, opacity=0.6)
fig.show()

How would I stack this data on top of each other?

By year:

ax = sns.catplot(x='Year',kind='count',data=tv_shows_df,orient="h",height=30,aspect=2)
ax.fig.suptitle('Number of TV series per year')
ax.fig.autofmt_xdate()

DF Form:

year_df = tv_shows_df.groupby('Year')
year_sum =tv_shows_df.groupby('Year').sum()
year_sum = year_sum[['Netflix', 'Hulu', 'Prime Video', 'Disney+']]

Top production years:

year_sum.columns

Index(['Netflix', 'Hulu', 'Prime Video', 'Disney+'], dtype='object')

Trying to see which years producted the most movies that are on the streaming service...not going well

year_sum.iloc[0].value_counts()

0    3
2    1
Name: 1901, dtype: int64

year_sum['Year'] = year_sum.index

year_sum['Year']

Year
1901    1901
1904    1904
1914    1914
1931    1931
1932    1932
        ... 
2016    2016
2017    2017
2018    2018
2019    2019
2020    2020
Name: Year, Length: 81, dtype: int64

year_sum['Year'].describe()

count      81.000000
mean     1978.148148
std        27.260370
min      1901.000000
25%      1960.000000
50%      1980.000000
75%      2000.000000
max      2020.000000
Name: Year, dtype: float64

year_sum.Year.sort_values()

Year
1901    1901
1904    1904
1914    1914
1931    1931
1932    1932
        ... 
2016    2016
2017    2017
2018    2018
2019    2019
2020    2020
Name: Year, Length: 81, dtype: int64

year_sum[0:3].sort_index(ascending=False)

	Netflix	Hulu	Prime Video	Disney+	Year
Year
1914	1	0	0	0	1914
1904	0	0	1	0	1904
1901	0	0	2	0	1901

year_sum.columns

Index(['Netflix', 'Hulu', 'Prime Video', 'Disney+', 'Year'], dtype='object')

year_sum.drop(columns='Year', inplace=True)

recent_year_sum = year_sum.sort_index(ascending=False).head(15)
recent_year_sum

	Netflix	Hulu	Prime Video	Disney+
Year
2020	110	41	18	8
2019	233	109	36	22
2018	272	139	155	13
2017	221	132	305	19
2016	219	134	231	10
2015	180	132	161	9
2014	137	128	125	8
2013	92	111	111	7
2012	88	106	119	12
2011	80	93	92	6
2010	54	80	90	5
2009	44	61	67	4
2008	29	44	62	4
2007	26	39	43	3
2006	21	48	38	6

year_sum.sort_values(by='Netflix', ascending=False).head(10)

	Netflix	Hulu	Prime Video	Disney+
Year
2018	272	139	155	13
2019	233	109	36	22
2017	221	132	305	19
2016	219	134	231	10
2015	180	132	161	9
2014	137	128	125	8
2020	110	41	18	8
2013	92	111	111	7
2012	88	106	119	12
2011	80	93	92	6

year_sum['Sum'] = year_sum.sum(axis=1)

year_sum

	Netflix	Hulu	Prime Video	Disney+	Sum
Year
1901	0	0	2	0	2
1904	0	0	1	0	1
1914	1	0	0	0	1
1931	0	1	0	0	1
1932	0	0	1	0	1
...	...	...	...	...	...
2016	219	134	231	10	594
2017	221	132	305	19	677
2018	272	139	155	13	579
2019	233	109	36	22	400
2020	110	41	18	8	177

81 rows × 5 columns

year_sum.sort_values(by='Sum', ascending=False).head(10)

	Netflix	Hulu	Prime Video	Disney+	Sum
Year
2017	221	132	305	19	677
2016	219	134	231	10	594
2018	272	139	155	13	579
2015	180	132	161	9	482
2019	233	109	36	22	400
2014	137	128	125	8	398
2012	88	106	119	12	325
2013	92	111	111	7	321
2011	80	93	92	6	271
2010	54	80	90	5	229

Finally, top 10 years of show releases.

sns.lineplot(data=year_sum['Sum']);

sns.lineplot(data=year_sum['Netflix']);
sns.lineplot(data=year_sum['Prime Video']);

recent = year_sum.copy()

recent = year_sum[year_sum.index >= 2000]

recent.drop(columns='Sum', inplace=True)
recent

	Netflix	Hulu	Prime Video	Disney+
Year
2000	6	14	21	3
2001	7	19	28	3
2002	12	18	21	1
2003	11	20	25	2
2004	10	28	44	2
2005	15	43	49	2
2006	21	48	38	6
2007	26	39	43	3
2008	29	44	62	4
2009	44	61	67	4
2010	54	80	90	5
2011	80	93	92	6
2012	88	106	119	12
2013	92	111	111	7
2014	137	128	125	8
2015	180	132	161	9
2016	219	134	231	10
2017	221	132	305	19
2018	272	139	155	13
2019	233	109	36	22
2020	110	41	18	8

sns.lineplot(data=recent);

sns.lineplot(data=recent['Netflix']);

#alternatively:


x=recent.axes[0]
y=recent["Netflix"]
plt.figure(figsize=(12,8))
plt.plot(x,y,linestyle='solid',label="count of TV shows")
plt.xticks(x, x, rotation=75)
plt.ylabel("Count")
plt.xlabel("Years")
plt.legend()
plt.title("Count of Netflix TV shows by Year")
plt.grid(color='b', linestyle='dotted', linewidth=2)
plt.show()

This route created a dataframe of only Sherlock

sherlock = tv_shows_df.loc[tv_shows_df['Title']=='Sherlock']
sherlock

	Title	Year	Age	IMDb	Rotten Tomatoes	Netflix	Hulu	Prime Video	Disney+	type
3	Sherlock	2010	16+	9.1	78.0	1	0	0	0	1

df.loc[df[‘column name’] condition]

This route just outputs the row.

tv_shows_df.loc[tv_shows_df['Title']=='Sherlock']

	Title	Year	Age	IMDb	Rotten Tomatoes	Netflix	Hulu	Prime Video	Disney+	type
3	Sherlock	2010	16+	9.1	78.0	1	0	0	0	1

tv_shows_df.head()

	Title	Year	Age	IMDb	Rotten Tomatoes	Netflix	Hulu	Prime Video	Disney+	type
0	Breaking Bad	2008	18+	9.5	96.0	1	0	0	0	1
1	Stranger Things	2016	16+	8.8	93.0	1	0	0	0	1
2	Money Heist	2017	18+	8.4	91.0	1	0	0	0	1
3	Sherlock	2010	16+	9.1	78.0	1	0	0	0	1
4	Better Call Saul	2015	18+	8.7	97.0	1	0	0	0	1

Used: https://www.kaggle.com/osmanballi/analysis-of-tv-shows-sns-go-pyplot https://www.kaggle.com/nishadjoshi98/visualization-analysis-and-recommendation-system https://www.kaggle.com/sreshta140/a-quick-analysis-on-tv-shows for inspiration